The blind source separation problem is to extract the underlying source signals from a set of linear mixtures, where the mixing matrix is unknown. This situation is common in acoustics, radio, medical signal and image processing, hyperspectral imaging, etc.
Examples
1-dimensional case: separation of linearly mixed audio signals.
- Sources - 7 audio source signals
(each of 7 mixtures is 5 sec. duration, MP3 format) - Mixtures - mixed audio signals from 7 sources
- Separated signals - audio sources blindly separated from the mixtures
 |
 |
|||
| SOURCE 1 | SOURCE 2 | |||
 |
 |
|||
| MIXTURE 1 | MIXTURE 2 | |||
 |
 |
|||
| ESTIMATED SOURCE 1 | ESTIMATED SOURCE 2 | |||
|
Figure 1: blind separation of two 2D linear mixtures |
||||
RELATED ARTICLES:
- Zibulevsky, M. and Pearlmutter, B.A. (1999). "Blind Source Separation by Sparse Decomposition ", Neural Computations 13(4), 2001
[ZIPPed PS] [gZIPPed PS] - M. Zibulevsky, Y.Y. Zeevi (2001). "Extraction of a single source from multichannel data using sparse decomposition"
[gZIPPed PS] - P. Kisilev, M. Zibulevsky, Y.Y. Zeevi, B.A. Pearlmutter (2000). "Multiresolution framework for blind source separation"
[gZIPPed PS] - Akaysha C. Tang, Barak A. Pearlmutter, and Michael Zibulevsky. Blind source separation of neuromagnetic responses. Computational Neuroscience 1999, proceedings published in Neurocomputing. In press.